The dream of the 90’s is alive in Portland… and perhaps in Flo, a new video-creation app that promises to use AI & voice commands to synthesize great movies from unwashed source material:
Just request a story by location, time period, tags or all of the above and Flo will respond to you like your very own video making assistant, creating the video story of your choice—e.g. ‘Make me a video story of my cat’ or ‘Make a video of my weekend trip to the beach’.
I’m off to try it out, but color me skeptical: My Emmy-winning colleague Bill Hensler, who used to head up video engineering at Adobe, said he’d been pitched similar tech since the early 90’s and always said, “Sure, just show me a system that can match a shot of a guy entering a room with another shot of the same thing from a different angle—then we’ll talk.” As far as I know, we’re still waiting.
No word yet on what happens if you invite Flo to kiss your grits. (Also, saying this makes me Very Old.)
Baidu’s Deep Voice 2 can eerily render sentences with numerous accents & other unique quirks; click through to hear examples.
In only three months, we’ve been able to scale our system from 20 hours of speech and a single voice to hundreds of hours with hundreds of voices. Deep Voice 2 can learn from hundreds of voices and imitate them perfectly. Unlike traditional systems, which need dozens of hours of audio from a single speaker, Deep Voice 2 can learn from hundreds of unique voices from less than half an hour of data per speaker, while achieving high audio quality.
Conversely, Anti AI AI is a wearable detector of synthetic voices:
The device notifies the wearer when a synthetic voice is detected and cools the skin using a thermoelectric plate to alert the wearer the voice they are hearing was synthesised: by a cold, lifeless machine.
To quote the stoney falsetto of Towlie, “I have no idea what’s goin’ on right now…”
“Automatic colorization is a fundamentally ambiguous problem,” says UC Berkeley researcher Richard Zhang. “What humans do well + what computers do well = better than either alone,” say I. With that in mind, check out this new research project that pairs AI with human-powered adjustments to deliver compelling results quickly:
Like a Tracy Jordan joint, this is Hard To Watch: ADAC, “the German equivalent of AAA… usually crash tests real cars at their facility in Landsberg, Germany,” but in this case put a 2,700-piece Lego Porsche to the test at 28mph:
“The challenge was now to test this small car in the normal crash system and still produce the most realistic damage possible,” explains Johannes Heilmaier, head of the crash system at the ADAC Technikzentrum. “We developed a crash set-up like for any other car – just in mini format.” [details]
Over the 10 days we took photos of yellow cabs whenever we had time to from as many different angles as possible. So we gathered 2000 (!) photos in total we had to sort afterwards and compile to a hyperlapse around a cab in post production. It took us 5 whole days in post production to get this one shot.
Whether or note you’re compelled by the story of caffeine addiction & the migraines brought on by withdrawal, I think you’ll find this animation captivating & will want to see The White Stripes sign the production team stat.
I’m wondering, though, about these devices’ ability to help us find & be our better selves. Could something like Google’s One Today charitable app offer bite-sized daily info, sharing the voices of people in needs & asking for you to kick in a couple of bucks to their aid? I’m not sure—but I like the possibilities that are opening up.
I find this so oddly delightful—and kind of the polar opposite of my car’s door handles.
See, the latter are supposed to be magical, automatically popping out when I approach the car. In practice, though, they’re unreliable enough (e.g. when my key is buried in my pocket, which of course is inevitably when my hands are full) that the they feel like a net negative. Something that used to work just fine, and that is now supposed to be an improvement, leaves me stressed & a bit bummed out.
Smart Replies are on the opposite end of the spectrum: They never used to exist, and even when they aren’t relevant, I’m reminded of the old bit about a dog walking on its hind legs: It’s not done well, but you’re charmed to see it done at all.
Anyway, you can check it out today in Gmail on Android and iOS:
Smart Reply utilizes machine learning to give you better responses the more you use it. So if you’re more of a “thanks!” than a “thanks.” person, we’ll suggest the response that’s, well, more you! If you want to learn about the smarts behind Smart Reply, check out the Google Research Blog.
And yes, you should now have email exchanges with colleagues composed entirely of Smart Replies. “Thanks, I will!” 🙂
Using our machine learning technology, Google Photos will not only remind you to share—it will automatically select the right photos, and even suggest who you should send them to based on who was in the photos. Just tap send, and your friends and family will see all your photos, and get a reminder to add theirs too.
Maps’ Android app will now show Street View images of every road you’re supposed to turn onto. If you tap the image, Street View will open up to that location, showing an arrow in the direction you’re meant to turn. […]
Google’s iOS app usually has the same look and features, so it may just be a matter of time before it gets updated.
Today, Google is introducing a feature in Allo that uses a combination of neural networks and the work of artists to turn your selfie into a personalized sticker pack. Simply snap a selfie, and it’ll return an automatically generated illustrated version of you, on the fly, with customization options to help you personalize the stickers even further.
“Take a human desire,” says Twitter co-founder Evan Williams, “preferably one that has been around for a really long time…Identify that desire and use modern technology to take out steps.”
It’s interesting to think about this as Instagram’s identity has evolved in a “lol nothing matters” Snapchat world. (I initially typed “Snapshat”; Freudian?). Founder Kevin Systrom used to like to describe the product as “a visual walkie talkie,” but plainly that wasn’t true. As their head of product Kevin Weil said, “It became a place where people kept raising the bar on themselves in terms of the quality of what they had to achieve to post. We didn’t want that.” If you haven’t yet, listen to the This American Life episode about teenage girls’ Instagram anxiety referenced in “The Instagram lobster trap.”
Anyway, Instagram has found that lowering the bar—creating an impermanent, low-stress complement to one’s highlight reel—is key. They need bottom-up activity to make things work:
“Your connections with your friends and your family are the thing that make Instagram work. All the data supports that if you follow more friends and engage with your friends, your activity goes through the roof. If you just follow more celebrity content or more interest-based content, that doesn’t move the needle at all.” – Kevin Systrom, Instagram co-founder
There are millions of people who will post beautiful pictures of coffee or 1960s office blocks, or like a photo by a celebrity, but there are billions who’ll share a snapshot of their lunch, beer, dog or child. Instagram is moving to capture that in the same way Messenger and WhatsApp captured chat.
Shooting Pano LA has been the most ambitious, challenging, demanding, and rewarding project I have worked on to date. It was shot over a period of two years entirely in true panoramic form using two synced DSLR cameras side by side. The resulting panoramic timelapse footage comes in at a whopping 10K x 4K resolution when stitched. Continue reading →
Starting today, people can go to photos.google.com/mothersday, pick a mom and kids, and then Google Photos does the rest. It automatically chooses the best photos of the mother and children, and sets it all to music to make a personalized movie. If you want to remove any of the photos or add others, you can make adjustments on Android or iOS.
Here’s the one I made for my mom featuring her grandsons:
Days of miracles and wonder—always. (Editing audio just like a text doc is particularly spooky, especially in light of voice simulation on demand.)
The SIGGRAPH Technical Papers program is the premier international forum for disseminating new scholarly work in computer graphics and interactive techniques. SIGGRAPH 2017 brings together thousands of computer graphics professionals, 30 July – 3 August 2017 in Los Angeles, California, USA.
To sell his ’96 Suzuki Vitara, and spoof the absurdity of car commercials, Eugene Romanovsky put together an epic video showcasing the heroic powers of his clunky 20-year-old car. This car has been everywhere. There are cameos from Jurassic Park, Mad Max: Fury Road, and even a scene on the moon. This is perhaps the most convincing ad we’ve ever seen–just try to watch it and not come away feeling that this is the car for you. [Via]
Tangentially reminds me of when my friend (and compositing hoss) Dave Werner got a hold of our son Finn’s “Dancing Robot” preschool dance moves:
Sales Wick is a pilot for SWISS and while working an overnight flight from Zurich to Sao Paulo, he filmed the first segment of the flight from basically the dashboard of the plane and made a timelapse video out of it. At that altitude, without a lot of light and atmospheric interference, the Milky Way is super vivid.
Make sure to stick around at least til the ~1:25 mark when other aircraft begin zooming past.